Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking

Validation of Step Detection and Distance Calculation Algorithms for Soccer Performance Monitoring

This study focused on developing and evaluating a gyroscope-based step counter algorithm using inertial measurement unit (IMU) readings for precise athletic performance monitoring in soccer. The research aimed to provide reliable step detection and distance estimation tailored to soccer-specific movements, including various running speeds and directional changes. Real-time algorithms utilizing shank angular data from gyroscopes were created. Experiments were conducted on a specially designed soccer-specific testing circuit performed by 15 athletes, simulating a range of locomotion activities such as walking, jogging, and high-intensity actions. The algorithm outcome was compared with manually tagged data from a high-quality video camera-based system for validation, by assessing the agreement between the paired values using limits of agreement, concordance correlation coefficient, and further metrics. Results returned a step detection accuracy of 95.8% and a distance estimation Root Mean Square Error (RMSE) of 17.6 m over about 202 m of track. A sub-sample (N = 6) also wore two pairs of devices concurrently to evaluate inter-unit reliability. The performance analysis suggested that the algorithm was effective and reliable in tracking diverse soccer-specific movements. The proposed algorithm offered a robust and efficient solution for tracking step count and distance covered in soccer, particularly beneficial in indoor environments where global navigation satellite systems are not feasible. This advancement in sports technology widens the spectrum of tools for coaches and athletes in monitoring soccer performance.

Conversational Speech Behaviors Are Context Dependent

PURPOSE

According to the interpersonal synergy model of spoken dialogue, interlocutors modify their communicative behaviors to meet the contextual demands of a given conversation. Although a growing body of research supports this postulation for linguistic behaviors (e.g., semantics, syntax), little is understood about how this model applies to speech behaviors (e.g., speech rate, pitch). The purpose of this study is to test the hypothesis that interlocutors adjust their speech behaviors across different conversational tasks with different conversational goals.

METHOD

In this study, 28 participants each engaged in two different types of conversations (i.e., relational and informational) with two partners (i.e., Partner 1 and Partner 2), yielding a total of 112 conversations. We compared six acoustic measures of participant speech behavior across conversational task and partner.

RESULTS

Linear mixed-effects models demonstrated significant differences between speech feature measures in informational and relational conversations. Furthermore, these findings were generally robust across conversations with different partners.

CONCLUSIONS

Results suggest that contextual demands influence speech behaviors. These findings provide empirical support for the interpersonal synergy model and highlight important considerations for assessing speech behaviors in individuals with communication disorders.

Fall prediction in a quiet standing balance test via machine learning: Is it possible?

The elderly population is growing rapidly in the world and falls are becoming a big problem for society. Currently, clinical assessments of gait and posture include functional evaluations, objective, and subjective scales. They are considered the gold standard to indicate optimal mobility and performance individually, but their sensitivity and specificity are not good enough to predict who is at higher risk of falling. An innovative approach for fall prediction is the machine learning. Machine learning is a computer-science area that uses statistics and optimization methods in a large amount of data to make outcome predictions. Thus, to assess the performance of machine learning algorithms in classify participants by age, number of falls and falls frequency based on features extracted from a public database of stabilometric assessments. 163 participants (116 women and 47 men) between 18 and 85 years old, 44.0 to 75.9 kg mass, 140.0 to 189.8 cm tall, and 17.2 to 31.9 kg/m2 body mass index. Six different machine learning algorithms were tested for this classification, which included Logistic Regression, Linear Discriminant Analysis, K Nearest-neighbours, Decision Tree Classifier, Gaussian Naive Bayes and C-Support Vector Classification. The machine learning algorithms were applied in this database which has sociocultural, demographic, and health status information about participants. All algorithm models were able to classify the participants into young or old, but our main goal was not achieved, no model identified participants at high risk of falling. Our conclusion corroborates other works in the biomechanics field, arguing the static posturography, probably due to the low daily living activities specificity, does not have the desired effects in predicting the risk of falling. Further studies should focus on dynamic posturography to assess the risk of falls.

Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors

The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.

Classification of human walking context using a single-point accelerometer

Real-world walking data offers rich insights into a person's mobility. Yet, daily life variations can alter these patterns, making the data challenging to interpret. As such, it is essential to integrate context for the extraction of meaningful information from real-world movement data. In this work, we leveraged the relationship between the characteristics of a walking bout and context to build a classification algorithm to distinguish between indoor and outdoor walks. We used data from 20 participants wearing an accelerometer on the thigh over a week. Their walking bouts were isolated and labeled using GPS and self-reporting data. We trained and validated two machine learning models, random forest and ensemble Support Vector Machine, using a leave-one-participant-out validation scheme on 15 subjects. The 5 remaining subjects were used as a testing set to choose a final model. The chosen model achieved an accuracy of 0.941, an F1-score of 0.963, and an AUROC of 0.931. This validated model was then used to label the walks from a different dataset with 15 participants wearing the same accelerometer. Finally, we characterized the differences between indoor and outdoor walks using the ensemble of the data. We found that participants walked significantly faster, longer, and more continuously when walking outdoors compared to indoors. These results demonstrate how movement data alone can be used to obtain accurate information on important contextual factors. These factors can then be leveraged to enhance our understanding and interpretation of real-world movement data, providing deeper insights into a person's health.

Kinematic Analysis of Human Gait in Healthy Young Adults Using IMU Sensors: Exploring Relevant Machine Learning Features for Clinical Applications

BACKGROUND

Gait is the manner or style of walking, involving motor control and coordination to adapt to the surrounding environment. Knowing the kinesthetic markers of normal gait is essential for the diagnosis of certain pathologies or the generation of intelligent ortho-prostheses for the treatment or prevention of gait disorders. The aim of the present study was to identify the key features of normal human gait using inertial unit (IMU) recordings in a walking test.

METHODS

Gait analysis was conducted on 32 healthy participants (age range 19-29 years) at speeds of 2 km/h and 4 km/h using a treadmill. Dynamic data were obtained using a microcontroller (Arduino Nano 33 BLE Sense Rev2) with IMU sensors (BMI270). The collected data were processed and analyzed using a custom script (MATLAB 2022b), including the labeling of the four relevant gait phases and events (Stance, Toe-Off, Swing, and Heel Strike), computation of statistical features (64 features), and application of machine learning techniques for classification (8 classifiers).

RESULTS

Spider plot analysis revealed significant differences in the four events created by the most relevant statistical features. Among the different classifiers tested, the Support Vector Machine (SVM) model using a Cubic kernel achieved an accuracy rate of 92.4% when differentiating between gait events using the computed statistical features.

CONCLUSIONS

This study identifies the optimal features of acceleration and gyroscope data during normal gait. The findings suggest potential applications for injury prevention and performance optimization in individuals engaged in activities involving normal gait. The creation of spider plots is proposed to obtain a personalised fingerprint of each patient's gait fingerprint that could be used as a diagnostic tool. A deviation from a normal gait pattern can be used to identify human gait disorders. Moving forward, this information has potential for use in clinical applications in the diagnosis of gait-related disorders and developing novel orthoses and prosthetics to prevent falls and ankle sprains.

Using Lower Limb Wearable Sensors to Identify Gait Modalities: A Machine-Learning-Based Approach

Real-world gait analysis can aid in clinical assessments and influence related interventions, free from the restrictions of a laboratory setting. Using individual accelerometers, we aimed to use a simple machine learning method to quantify the performance of the discrimination between three self-selected cyclical locomotion types using accelerometers placed at frequently referenced attachment locations. Thirty-five participants walked along a 10 m walkway at three different speeds. Triaxial accelerometers were attached to the sacrum, thighs and shanks. Slabs of magnitude, three-second-long accelerometer data were transformed into two-dimensional Fourier spectra. Principal component analysis was undertaken for data reduction and feature selection, followed by discriminant function analysis for classification. Accuracy was quantified by calculating scalar accounting for the distances between the three centroids and the scatter of each category's cloud. The algorithm could successfully discriminate between gait modalities with 91% accuracy at the sacrum, 90% at the shanks and 87% at the thighs. Modalities were discriminated with high accuracy in all three sensor locations, where the most accurate location was the sacrum. Future research will focus on optimising the data processing of information from sensor locations that are advantageous for practical reasons, e.g., shank for prosthetic and orthotic devices.

Towards Environment-Aware Fall Risk Assessment: Classifying Walking Surface Conditions Using IMU-Based Gait Data and Deep Learning

Fall risk assessment (FRA) helps clinicians make decisions about the best preventative measures to lower the risk of falls by identifying the different risks that are specific to an individual. With the development of wearable technologies such as inertial measurement units (IMUs), several free-living FRA methods based on fall predictors derived from IMU-based data have been introduced. The performance of such methods could be improved by increasing awareness of the individuals' walking environment. This study aims to introduce and analyze a 25-layer convolutional neural network model for classifying nine walking surface conditions using IMU-based gait data, providing a basis for environment-aware FRAs. A database containing data collected from thirty participants who wore six IMU sensors while walking on nine surface conditions was employed. A systematic analysis was conducted to determine the effects of gait signals (acceleration, magnetic field, and rate of turn), sensor placement, and signal segment size on the method's performance. Accuracies of 0.935 and 0.969 were achieved using a single and dual sensor, respectively, reaching an accuracy of 0.971 in the best-case scenario with optimal settings. The findings and analysis can help to develop more reliable and interpretable fall predictors, eventually leading to environment-aware FRA methods.

Recognition of walking directional intention employed ground reaction forces and center of pressure during gait initiation

BACKGROUND

Movement intentions are generally classified by Electroencephalogram (EEG) and have been used in gait initiation prediction. However, it is not easy to collect EEG data and practical in reality. Alternatively, ground reaction force (GRF) and the center of pressure (COP) is produced by the contact between the foot and the ground during a specific period of walking, which are the characteristics of evaluating gait performance RESEARCH QUESTION: The study aims to use a deep learning technique to recognize the data of the COP and GRF to classify straight walking and right turn. Second, the study aims to reveal gait characteristics that could replace EEG to predict walking directional intentions METHODS: Ten healthy male adults were instructed to stand on the force platform and self-selected to perform three conditions: standstill, straight walking, and right turn. The onset of gait initiation was evaluated by muscle activation of the right tibialis anterior, and EEG and the COP displacement evaluated the onset of gait intention. Subsequently, GRF and COP would be treated as features to classify the gait intention in the Long Short-Term Memory (LSTM) model.

RESULTS

The results revealed that the onset of EEG and the COP displacement initiation were statistically significant differences between straight walking and right turn. For the classification, the average accuracy of the LSTM model with GRF and COP as features reached the highest one, 94.79 %, depending on the heel- or toe-off of the swing leg. The results indicated that gait intentions could be classified based on the GRF and COP.

SIGNIFICANCE

The machine learning technique of LSTM with gait parameters can recognize the gait intention of changing walking orientation. Our model and approach would be expected to provide advanced predictions, such as exoskeleton control or pedestrian traffic flow.

Foot Pronation Prediction with Inertial Sensors during Running: A Preliminary Application of Data-Driven Approaches

Abnormal foot postures may affect foot movement and joint loading during locomotion. Investigating foot posture alternation during running could contribute to injury prevention and foot mechanism study. This study aimed to develop feature-based and deep learning algorithms to predict foot pronation during prolonged running. Thirty-two recreational runners have been recruited for this study. Nine-axial inertial sensors were attached to the right dorsum of the foot and the vertical axis of the distal anteromedial tibia. This study employed feature-based machine learning algorithms, including support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and deep learning, i.e., one-dimensional convolutional neural networks (CNN1D), to predict foot pronation. A custom nested k-fold cross-validation was designed for hyper-parameter tuning and validating the model's performance. The XGBoot classifier achieved the best accuracy using acceleration and angular velocity data from the foot dorsum as input. Accuracy and the area under curve (AUC) were 74.7 ± 5.2% and 0.82 ± 0.07 for the subject-independent model and 98 ± 0.4% and 0.99 ± 0 for the record-wise method. The test accuracy of the CNN1D model with sensor data at the foot dorsum was 74 ± 3.8% for the subject-wise approach with an AUC of 0.8 ± 0.05. This study found that these algorithms, specifically for the CNN1D and XGBoost model with inertial sensor data collected from the foot dorsum, could be implemented into wearable devices, such as a smartwatch, for monitoring a runner's foot pronation during long-distance running. It has the potential for running shoe matching and reducing or preventing foot posture-induced injuries.

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1-Data From Wearable Devices

OBJECTIVES

With the emerging use of machine learning (ML) techniques, there has been particular interest in using wearable data for health economics and outcomes research (HEOR). We aimed to understand the emerging patterns of how ML has been applied to wearable data in HEOR.

METHODS

We identified studies published in PubMed between January 2016 and March 2021. Studies that included at least 1 HEOR-related Medical Subject Headings term, applied an ML, and used wearable data were eligible for inclusion. Two reviewers abstracted information including ML application types and data on which ML was applied and analyzed them using descriptive analyses.

RESULTS

A total of 148 studies were identified from PubMed, among which 32 studies met the inclusion criteria. There has been an increase over time in the number of ML studies using wearable data. ML has been more frequently used for monitoring events in real time (78%) than to predict future events (22%). There has been a wide range of outcomes examined, ranging from general physical or mental health (24%) to more disease-specific outcomes (eg, disease incidence [19%] and progression [13%]) and treatment-related outcomes (eg, treatment adherence [9%] and outcomes [9%]). Data for ML models were more often derived from wearable devices with specific medical purposes (60%) than those without (40%).

CONCLUSION

There has been a wide range of applications of ML to wearable data. Both medical and nonmedical wearable devices have been used as a data source, showing the potential for providing rich data for ML studies in HEOR.

Identifying Gait-Related Functional Outcomes in Post-Knee Surgery Patients Using Machine Learning: A Systematic Review

Modern lifestyles require new tools for determining a person's ability to return to daily activities after knee surgery. These quantitative instruments must feature high discrimination, be non-invasive, and be inexpensive. Machine learning is a revolutionary approach that has the potential to satisfy the aforementioned requirements and bridge the knowledge gap. The scope of this study is to summarize the results of a systematic literature review on the identification of gait-related changes and the determination of the functional recovery status of patients after knee surgery using advanced machine learning algorithms. The current systematic review was conducted using multiple databases in accordance with the PRISMA guidelines, including Scopus, PubMed, and Semantic Scholar. Six out of the 405 articles met our inclusion criteria and were directly related to the quantification of the recovery status using machine learning and gait data. The results were interpreted using appropriate metrics. The results demonstrated a recent increase in the use of sophisticated machine learning techniques that can provide robust decision-making support during personalized post-treatment interventions for knee-surgery patients.

Egocentric vision-based detection of surfaces: towards context-aware free-living digital biomarkers for gait and fall risk assessment

Background

Falls in older adults are a critical public health problem. As a means to assess fall risks, free-living digital biomarkers (FLDBs), including spatiotemporal gait measures, drawn from wearable inertial measurement unit (IMU) data have been investigated to identify those at high risk. Although gait-related FLDBs can be impacted by intrinsic (e.g., gait impairment) and/or environmental (e.g., walking surfaces) factors, their respective impacts have not been differentiated by the majority of free-living fall risk assessment methods. This may lead to the ambiguous interpretation of the subsequent FLDBs, and therefore, less precise intervention strategies to prevent falls.

Methods

With the aim of improving the interpretability of gait-related FLDBs and investigating the impact of environment on older adults’ gait, a vision-based framework was proposed to automatically detect the most common level walking surfaces. Using a belt-mounted camera and IMUs worn by fallers and non-fallers (mean age 73.6 yrs), a unique dataset (i.e., Multimodal Ambulatory Gait and Fall Risk Assessment in the Wild (MAGFRA-W)) was acquired. The frames and image patches attributed to nine participants’ gait were annotated: (a) outdoor terrains: pavement (asphalt, cement, outdoor bricks/tiles), gravel, grass/foliage, soil, snow/slush; and (b) indoor terrains: high-friction materials (e.g., carpet, laminated floor), wood, and tiles. A series of ConvNets were developed: EgoPlaceNet categorizes frames into indoor and outdoor; and EgoTerrainNet (with outdoor and indoor versions) detects the enclosed terrain type in patches. To improve the framework’s generalizability, an independent training dataset with 9,424 samples was curated from different databases including GTOS and MINC-2500, and used for pretrained models’ (e.g., MobileNetV2) fine-tuning.

Results

EgoPlaceNet detected outdoor and indoor scenes in MAGFRA-W with 97.36$$\%$$ % and 95.59$$\%$$ % (leave-one-subject-out) accuracies, respectively. EgoTerrainNet-Indoor and -Outdoor achieved high detection accuracies for pavement (87.63$$\%$$ % ), foliage (91.24$$\%$$ % ), gravel (95.12$$\%$$ % ), and high-friction materials (95.02$$\%$$ % ), which indicate the models’ high generalizabiliy.

Conclusions

Encouraging results suggest that the integration of wearable cameras and deep learning approaches can provide objective contextual information in an automated manner, towards context-aware FLDBs for gait and fall risk assessment in the wild.

A machine learning approach for the identification of kinematic biomarkers of chronic neck pain during single- and dual-task gait

BACKGROUND

Changes in gait characteristics have been reported in people with chronic neck pain (CNP).

RESEARCH QUESTION

Can we classify people with and without CNP by training machine learning models with Inertial Measurement Units (IMU)-based gait kinematic data?

METHODS

Eighteen asymptomatic individuals and 21 participants with CNP were recruited for the study and performed two gait trajectories, (1) linear walking with their head straight (single-task) and (2) linear walking with continuous head-rotation (dual-task). Kinematic data were recorded from three IMU sensors attached to the forehead, upper thoracic spine (T1), and lower thoracic spine (T12). Temporal and spectral features were extracted to generate the dataset for both single- and dual-task gait. To evaluate the most significant features and simultaneously reduce the dataset size, the Neighbourhood Component Analysis (NCA) method was utilized. Three supervised models were applied, including K-Nearest Neighbour, Support Vector Machine, and Linear Discriminant Analysis to test the performance of the most important temporal and spectral features.

RESULTS

The performance of all classifiers increased after the implementation of NCA. The best performance was achieved by NCA-Support Vector Machine with an accuracy of 86.85%, specificity of 83.30%, and sensitivity of 92.85% during the dual-task gait using only nine features.

SIGNIFICANCE

The results present a data-driven approach and machine learning-based methods to identify test conditions and features from high-dimensional data obtained during gait for the classification of people with and without CNP.

Effects of Healthcare Technologies on the Promotion of Physical Activities in Older Persons: A Systematic Review

This study aimed to explore the effects of health technologies on the promotion of health through physical activities of older persons. Following PRISMA guidelines, a systematic review of relevant articles published prior to 2020 was conducted from selected indices such as COCHRANE, PubMed, Science Direct, Proquest, including the use of hand search procedure. Twenty-seven articles were analyzed with significant findings influential to older people nursing: types of health technologies used for promoting physical activity; effects of technology use in promoting physical activity of older person care; and aspects that need to be considered in technology use among older persons. Characteristics of technologies were accuracy, usefulness, reliability, comfort, safety, and relevancy. Most technologies promoting physical activities for older people were wearable technologies that use artificial intelligence. Altogether, these technologies influenced overall healthcare behaviors of older persons. With healthcare technology efficiencies, proficiencies, and dependencies, technology-based healthcare have served older people well. Most technologies for older people care, such as wearables, reliably produce characteristics enhancing dependency and accuracy of bio-behavioral information influencing physical activities of older persons. Health technologies foster the values of physical activities among older persons thereby promoting healthy living.

Recent Machine Learning Progress in Lower Limb Running Biomechanics With Wearable Technology: A Systematic Review

With the emergence of wearable technology and machine learning approaches, gait monitoring in real-time is attracting interest from the sports biomechanics community. This study presents a systematic review of machine learning approaches in running biomechanics using wearable sensors. Electronic databases were retrieved in PubMed, Web of Science, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect. A total of 4,068 articles were identified via electronic databases. Twenty-four articles that met the eligibility criteria after article screening were included in this systematic review. The range of quality scores of the included studies is from 0.78 to 1.00, with 40% of articles recruiting participant numbers between 20 and 50. The number of inertial measurement unit (IMU) placed on the lower limbs varied from 1 to 5, mainly in the pelvis, thigh, distal tibia, and foot. Deep learning algorithms occupied 57% of total machine learning approaches. Convolutional neural networks (CNN) were the most frequently used deep learning algorithm. However, the validation process for machine learning models was lacking in some studies and should be given more attention in future research. The deep learning model combining multiple CNN and recurrent neural networks (RNN) was observed to extract different running features from the wearable sensors and presents a growing trend in running biomechanics.

Generalizability of deep learning models for predicting outdoor irregular walking surfaces

Observations from laboratory-based gait analysis are difficult to extrapolate to real-world environments where gait behavior is modulated in response to complex environmental conditions and surface profiles. Inertial measurement units (IMUs) permit real-world gait analysis; however, automatic detection of surfaces encountered remains largely unexplored. The aims of this study are to quantify for machine learning models the effect of (1) random and subject-wise data splitting and (2) sensor location and count on surface classification performance. Thirty participants walked on nine surface conditions (flat-even, slope-up, slope-down, stairs-up, stairs-down, cobblestone, grass, banked-left, banked-right) wearing IMUs (wrist, trunk, bilateral thighs, bilateral shanks). Data were separated into gait cycles, normalized to 101 samples, and spilt into train and test sets (85 and 15%, respectively). For random splitting, trials were randomly assigned to the train or test set. In subject-wise splitting, all trials from 4 random participants were selected for testing. Linear discriminant analysis extracted features from the IMUs. Features were delivered to a neural network. F1-score evaluated model performance. Models achieved F1 scores of 0.96 and 0.78 using random and subject-wise splitting, respectively. Random splitting performance was mainly invariant to sensor location/count; however, subject-wise splitting showed best performance using lower-limb sensors. In general, stairs and sloped surfaces were easily predicted (F1 > 0.85) while banked surfaces were challenging, especially for subject-wise models (F1 ≈ 0.6). Neural networks can detect surfaces based on subtle changes in walking behavior captured by IMUs. Data splitting approaches and sensor location/count (subject-wise) have a non-negligible effect on model performance.

Deep learning approach to estimate foot pressure distribution in walking with application for a cost-effective insole system

Background

Foot pressure distribution can be used as a quantitative parameter for evaluating anatomical deformity of the foot and for diagnosing and treating pathological gait, falling, and pressure sores in diabetes. The objective of this study was to propose a deep learning model that could predict pressure distribution of the whole foot based on information obtained from a small number of pressure sensors in an insole.

Methods

Twenty young and twenty older adults walked a straight pathway at a preferred speed with a Pedar-X system in anti-skid socks. A long short-term memory (LSTM) model was used to predict foot pressure distribution. Pressure values of nine major sensors and the remaining 90 sensors in a Pedar-X system were used as input and output for the model, respectively. The performance of the proposed LSTM structure was compared with that of a traditionally used adaptive neuro-fuzzy interference system (ANFIS). A low-cost insole system consisting of a small number of pressure sensors was fabricated. A gait experiment was additionally performed with five young and five older adults, excluding subjects who were used to construct models. The Pedar-X system placed parallelly on top of the insole prototype developed in this study was in anti-skid socks. Sensor values from a low-cost insole prototype were used as input of the LSTM model. The accuracy of the model was evaluated by applying a leave-one-out cross-validation.

Results

Correlation coefficient and relative root mean square error (RMSE) of the LSTM model were 0.98 (0.92 ~ 0.99) and 7.9 ± 2.3%, respectively, higher than those of the ANFIS model. Additionally, the usefulness of the proposed LSTM model for fabricating a low-cost insole prototype with a small number of sensors was confirmed, showing a correlation coefficient of 0.63 to 0.97 and a relative RMSE of 12.7 ± 7.4%.

Conclusions

This model can be used as an algorithm to develop a low-cost portable smart insole system to monitor age-related physiological and anatomical alterations in foot. This model has the potential to evaluate clinical rehabilitation status of patients with pathological gait, falling, and various foot pathologies when more data of patients with various diseases are accumulated for training.

Human Activity Recognition of Individuals with Lower Limb Amputation in Free-Living Conditions: A Pilot Study

This pilot study aimed to investigate the implementation of supervised classifiers and a neural network for the recognition of activities carried out by Individuals with Lower Limb Amputation (ILLAs), as well as individuals without gait impairment, in free living conditions. Eight individuals with no gait impairments and four ILLAs wore a thigh-based accelerometer and walked on an improvised route in the vicinity of their homes across a variety of terrains. Various machine learning classifiers were trained and tested for recognition of walking activities. Additional investigations were made regarding the detail of the activity label versus classifier accuracy and whether the classifiers were capable of being trained exclusively on non-impaired individuals’ data and could recognize physical activities carried out by ILLAs. At a basic level of label detail, Support Vector Machines (SVM) and Long-Short Term Memory (LSTM) networks were able to acquire 77–78% mean classification accuracy, which fell with increased label detail. Classifiers trained on individuals without gait impairment could not recognize activities carried out by ILLAs. This investigation presents the groundwork for a HAR system capable of recognizing a variety of walking activities, both for individuals with no gait impairments and ILLAs.

Gait-based Human Identification through Minimum Gait-phases and Sensors

The incredible pace at which the world's elderly population is growing will put severe burdens on current healthcare systems and resources. To alleviate this concern the health care systems must rely on the transformation of eldercare and old homes to use Ambient Assisted Living (AAL). Human identification is one of the most common and critical tasks for condition monitoring, human-machine interaction, and providing assistive services in such environments. Recently, human gait has gained new attention as a biometric for identification to achieve contactless identification from a distance robust to physical appearances. However, an important aspect of gait identification through wearables and image-based systems alike is accurate identification when limited information is available for example, when only a fraction of the whole gait cycle or only a part of the subject's body is visible. In this paper, we present a gait identification technique based on temporal and descriptive statistic parameters of different gait phases as the features and we investigate the performance of using only single gait phases for the identification task using a minimum number of sensors. Gait data were collected from 60 individuals through pelvis and foot sensors. Six different machine learning algorithms were used for identification. It was shown that it is possible to achieve high accuracy of over 95.5% by monitoring a single phase of the whole gait cycle through only a single sensor. It was also shown that the proposed methodology could be used to achieve 100% identification accuracy when the whole gait cycle was monitored through pelvis and foot sensors combined. The ANN was found to be more robust to less number of data features compared to SVM and was concluded as the best machine algorithm for the purpose.

Applying deep neural networks and inertial measurement unit in recognizing irregular walking differences in the real world

Falling injuries pose serious health risks to people of all ages, and knowing the extent of exposure to irregular surfaces will increase the ability to measure fall risk. Current gait analysis methods require overly complicated instrumentation and have not been tested for external factors such as walking surfaces that are encountered in the real-world, thus the results are difficult to extrapolate to real-world situations. Artificial intelligence approaches (in particular deep learning networks of varied architectures) to analyze data collected from wearable sensors were used to identify irregular surface exposure in a real-world setting. Thirty young adults wore six Inertial Measurement Unit (IMU) sensors placed on their body (right wrist, trunks at the L5/S1 level, left and right thigh, left and right shank) while walking over eight different surfaces commonly encountered in the living community as well as occupational settings. Three variations of deep learning models were trained to solve this walking surface recognition problem: 1) convolution neural network (CNN); 2) long short term memory (LSTM) network and 3) LSTM structure with an extra global pooling layer (Global-LSTM) which learns the coordination between different data streams (e.g. different channels of the same sensor as well as different sensors). Results indicated that all three deep learning models can recognize walking surfaces with above 0.90 accuracy, with the Global-LSTM yielding the best performance at 0.92 accuracy. In terms of individual sensors, the right thigh based Global-LSTM model reported the highest accuracy (0.90 accuracy). Results from this study provide further evidence that deep learning and wearable sensors can be utilized to recognize irregular walking surfaces induced motion alteration and applied to prevent falling injuries.

Review of Wearable Devices and Data Collection Considerations for Connected Health

Wearable sensor technology has gradually extended its usability into a wide range of well-known applications. Wearable sensors can typically assess and quantify the wearer’s physiology and are commonly employed for human activity detection and quantified self-assessment. Wearable sensors are increasingly utilised to monitor patient health, rapidly assist with disease diagnosis, and help predict and often improve patient outcomes. Clinicians use various self-report questionnaires and well-known tests to report patient symptoms and assess their functional ability. These assessments are time consuming and costly and depend on subjective patient recall. Moreover, measurements may not accurately demonstrate the patient’s functional ability whilst at home. Wearable sensors can be used to detect and quantify specific movements in different applications. The volume of data collected by wearable sensors during long-term assessment of ambulatory movement can become immense in tuple size. This paper discusses current techniques used to track and record various human body movements, as well as techniques used to measure activity and sleep from long-term data collected by wearable technology devices.

Latest Research Trends in Fall Detection and Prevention Using Machine Learning: A Systematic Review

Falls are unusual actions that cause a significant health risk among older people. The growing percentage of people of old age requires urgent development of fall detection and prevention systems. The emerging technology focuses on developing such systems to improve quality of life, especially for the elderly. A fall prevention system tries to predict and reduce the risk of falls. In contrast, a fall detection system observes the fall and generates a help notification to minimize the consequences of falls. A plethora of technical and review papers exist in the literature with a primary focus on fall detection. Similarly, several studies are relatively old, with a focus on wearables only, and use statistical and threshold-based approaches with a high false alarm rate. Therefore, this paper presents the latest research trends in fall detection and prevention systems using Machine Learning (ML) algorithms. It uses recent studies and analyzes datasets, age groups, ML algorithms, sensors, and location. Additionally, it provides a detailed discussion of the current trends of fall detection and prevention systems with possible future directions. This overview can help researchers understand the current systems and propose new methodologies by improving the highlighted issues.

Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor

Wearable sensors facilitate running kinematics analysis of joint kinematics in real running environments. The use of a few sensors or, ideally, a single inertial measurement unit (IMU) is preferable for accurate gait analysis. This study aimed to use a convolutional neural network (CNN) to predict level-ground running kinematics (measured by four IMUs on the lower extremities) by using treadmill running kinematics training data measured using a single IMU on the anteromedial side of the right tibia and to compare the performance of level-ground running kinematics predictions between raw accelerometer and gyroscope data. The CNN model performed regression for intraparticipant and interparticipant scenarios and predicted running kinematics. Ten recreational runners were recruited. Accelerometer and gyroscope data were collected. Intraparticipant and interparticipant R² values of actual and predicted running kinematics ranged from 0.85 to 0.96 and from 0.7 to 0.92, respectively. Normalized root mean squared error values of actual and predicted running kinematics ranged from 3.6% to 10.8% and from 7.4% to 10.8% in intraparticipant and interparticipant tests, respectively. Kinematics predictions in the sagittal plane were found to be better for the knee joint than for the hip joint, and predictions using the gyroscope as the regressor were demonstrated to be significantly better than those using the accelerometer as the regressor.

IMU-Based Deep Neural Networks: Prediction of Locomotor and Transition Intentions of an Osseointegrated Transfemoral Amputee

This paper focuses on the design and comparison of different deep neural networks for the real-time prediction of locomotor and transition intentions of one osseointegrated transfemoral amputee using only data from inertial measurement units. The deep neural networks are based on convolutional neural networks, recurrent neural networks, and convolutional recurrent neural networks. The architectures' input are features in both the time domain and the time-frequency domain, which are derived from either one inertial measurement unit (placed above the prosthetic knee) or two inertial measurement units (placed above and below the prosthetic knee). The prediction of eight different locomotion modes (i.e., sitting, standing, level ground walking, stair ascent and descent, ramp ascent and descent, walking on uneven terrain) and the twenty-four transitions among them is investigated. The study shows that a recurrent neural network, realized with four layers of gated recurrent unit networks, achieves (with a 5-fold cross-validation) a mean F1 score of 84.78% and 86.50% using one inertial measurement unit, and 93.06% and 89.99% using two inertial measurement units, with or without sitting, respectively.

Artificial intelligence in dermatology and healthcare: An overview

Many aspects of our life are affected by technology. One of the most discussed advancements of modern technologies is artificial intelligence. It involves computational methods which in some way mimic the human thought process. Just like other branches, the medical field also has come under the ambit of artificial intelligence. Almost every field in medicine has been touched by its effect in one way or the other. Prominent among them are medical diagnosis, medical statistics, robotics, and human biology. Medical imaging is one of the foremost specialties with artificial intelligence applications, wherein deep learning methods like artificial neural networks are commonly used. artificial intelligence application in dermatology was initially restricted to the analysis of melanoma and pigmentary skin lesions, has now expanded and covers many dermatoses. Though the applications of artificial intelligence are ever increasing, large data requirements, interpretation of data and ethical concerns are some of its limitations in the present day.

Identifying Fatigue Indicators Using Gait Variability Measures: A Longitudinal Study on Elderly Brisk Walking

Real-time detection of fatigue in the elderly during physical exercises can help identify the stability and thus falling risks which are commonly achieved by the investigation of kinematic parameters. In this study, we aimed to identify the change in gait variability parameters from inertial measurement units (IMU) during a course of 60 min brisk walking which could lay the foundation for the development of fatigue-detecting wearable sensors. Eighteen elderly people were invited to participate in the brisk walking trials for 60 min with a single IMU attached to the posterior heel region of the dominant side. Nine sets of signals, including the accelerations, angular velocities, and rotation angles of the heel in three anatomical axes, were measured and extracted at the three walking times (baseline, 30th min, and 60th min) of the trial for analysis. Sixteen of eighteen participants reported fatigue after walking, and there were significant differences in the median acceleration (p = 0.001), variability of angular velocity (p = 0.025), and range of angle rotation (p = 0.0011), in the medial–lateral direction. In addition, there were also significant differences in the heel pronation angle (p = 0.005) and variability and energy consumption of the angles in the anterior–posterior axis (p = 0.028, p = 0.028), medial–lateral axis (p = 0.014, p = 0.014), and vertical axis (p = 0.002, p < 0.001). Our study demonstrated that a single IMU on the posterior heel of the dominant side can address the variability of kinematics parameters for elderly performing prolonged brisk walking and could serve as an indicator for walking instability, and thus fatigue.

Gait analysis in neurological populations: Progression in the use of wearables

Gait assessment is an essential tool for clinical applications not only to diagnose different neurological conditions but also to monitor disease progression as it contributes to the understanding of underlying deficits. There are established methods and models for data collection and interpretation of gait assessment within different pathologies. This narrative review aims to depict the evolution of gait assessment from observation and rating scales to wearable sensors and laboratory technologies and provide limitations and possible future directions in the field of gait assessment. In this context, we first present an extensive review of current clinical outcomes and gait models. Then, we demonstrate commercially available wearable technologies with their technical capabilities along with their use in gait assessment studies for various neurological conditions. In the next sections, a descriptive knowledge for existing inertial and EMG based algorithms and a sign based guide that shows the outcomes of previous neurological gait assessment studies are presented. Finally, we state a discussion for the use of wearables in gait assessment and speculate the possible research directions by revealing the limitations and knowledge gaps in the literature.

A Wearable Sensor System to Measure Step-Based Gait Parameters for Parkinson's Disease Rehabilitation

Spatiotemporal parameters of gait serve as an important biomarker to monitor gait impairments as well as to develop rehabilitation systems. In this work, we developed a computationally-efficient algorithm (SDI-Step) that uses segmented double integration to calculate step length and step time from wearable inertial measurement units (IMUs) and assessed its ability to reliably and accurately measure spatiotemporal gait parameters. Two data sets that included simultaneous measurements from wearable sensors and from a laboratory-based system were used in the assessment. The first data set utilized IMU sensors and a GAITRite mat in our laboratory to monitor gait in fifteen participants: 9 young adults (YA₁) (5 females, 4 males, age 23.6 ± 1 years), and 6 people with Parkinson's disease (PD) (3 females, 3 males, age 72.3 ± 6.6 years). The second data set, which was accessed from a publicly-available repository, utilized IMU sensors and an optoelectronic system to monitor gait in five young adults (YA₂) (2 females, 3 males, age 30.5 ± 3.5 years). In order to provide a complete representation of validity, we used multiple statistical analyses with overlapping metrics. Gait parameters such as step time and step length were calculated and the agreement between the two measurement systems for each gait parameter was assessed using Passing-Bablok (PB) regression analysis and calculation of the Intra-class Correlation Coefficient (ICC (2,1)) with 95% confidence intervals for a single measure, absolute-agreement, 2-way mixed-effects model. In addition, Bland-Altman (BA) plots were used to visually inspect the measurement agreement. The values of the PB regression slope were close to 1 and intercept close to 0 for both step time and step length measures. The results obtained using ICC (2,1) for step length showed a moderate to excellent agreement for YA (between 0.81 and 0.95) and excellent agreement for PD (between 0.93 and 0.98), while both YA and PD had an excellent agreement in step time ICCs (>0.9). Finally, examining the BA plots showed that the measurement difference was within the limits of agreement (LoA) with a 95% probability. Results from this preliminary study indicate that using the SDI-Step algorithm to process signals from wearable IMUs provides measurements that are in close agreement with widely-used laboratory-based systems and can be considered as a valid tool for measuring spatiotemporal gait parameters.

Deep Learning in Gait Parameter Prediction for OA and TKA Patients Wearing IMU Sensors

Quantitative assessments of patient movement quality in osteoarthritis (OA), specifically spatiotemporal gait parameters (STGPs), can provide in-depth insight into gait patterns, activity types, and changes in mobility after total knee arthroplasty (TKA). A study was conducted to benchmark the ability of multiple deep neural network (DNN) architectures to predict 12 STGPs from inertial measurement unit (IMU) data and to identify an optimal sensor combination, which has yet to be studied for OA and TKA subjects. DNNs were trained using movement data from 29 subjects, walking at slow, normal, and fast paces and evaluated with cross-fold validation over the subjects. Optimal sensor locations were determined by comparing prediction accuracy with 15 IMU configurations (pelvis, thigh, shank, and feet). Percent error across the 12 STGPs ranged from 2.1% (stride time) to 73.7% (toe-out angle) and overall was more accurate in temporal parameters than spatial parameters. The most and least accurate sensor combinations were feet-thighs and singular pelvis, respectively. DNNs showed promising results in predicting STGPs for OA and TKA subjects based on signals from IMU sensors and overcomes the dependency on sensor locations that can hinder the design of patient monitoring systems for clinical application.

Movement Estimation Using Soft Sensors Based on Bi-LSTM and Two-Layer LSTM for Human Motion Capture

The importance of estimating human movement has increased in the field of human motion capture. HTC VIVE is a popular device that provides a convenient way of capturing human motions using several sensors. Recently, the motion of only users’ hands has been captured, thereby greatly reducing the range of motion captured. This paper proposes a framework to estimate single-arm orientations using soft sensors mainly by combining a Bi-long short-term memory (Bi-LSTM) and two-layer LSTM. Positions of the two hands are measured using an HTC VIVE set, and the orientations of a single arm, including its corresponding upper arm and forearm, are estimated using the proposed framework based on the estimated positions of the two hands. Given that the proposed framework is meant for a single arm, if orientations of two arms are required to be estimated, the estimations are performed twice. To obtain the ground truth of the orientations of single-arm movements, two Myo gesture-control sensory armbands are employed on the single arm: one for the upper arm and the other for the forearm. The proposed framework analyzed the contextual features of consecutive sensory arm movements, which provides an efficient way to improve the accuracy of arm movement estimation. In comparison with the ground truth, the proposed method estimated the arm movements using a dynamic time warping distance, which was the average of 73.90% less than that of a conventional Bayesian framework. The distinct feature of our proposed framework is that the number of sensors attached to end-users is reduced. Additionally, with the use of our framework, the arm orientations can be estimated with any soft sensor, and good accuracy of the estimations can be ensured. Another contribution is the suggestion of the combination of the Bi-LSTM and two-layer LSTM.

Automatic Classification of Squat Posture Using Inertial Sensors: Deep Learning Approach

Without expert coaching, inexperienced exercisers performing core exercises, such as squats, are subject to an increased risk of spinal or knee injuries. Although it is theoretically possible to measure the kinematics of body segments and classify exercise forms with wearable sensors and algorithms, the current implementations are not sufficiently accurate. In this study, the squat posture classification performance of deep learning was compared to that of conventional machine learning. Additionally, the location for the optimal placement of sensors was determined. Accelerometer and gyroscope data were collected from 39 healthy participants using five inertial measurement units (IMUs) attached to the left thigh, right thigh, left calf, right calf, and lumbar region. Each participant performed six repetitions of an acceptable squat and five incorrect forms of squats that are typically observed in inexperienced exercisers. The accuracies of squat posture classification obtained using conventional machine learning and deep learning were compared. Each result was obtained using one IMU or a combination of two or five IMUs. When employing five IMUs, the accuracy of squat posture classification using conventional machine learning was 75.4%, whereas the accuracy using deep learning was 91.7%. When employing two IMUs, the highest accuracy (88.7%) was obtained using deep learning for a combination of IMUs on the right thigh and right calf. The single IMU yielded the best results on the right thigh, with an accuracy of 58.7% for conventional machine learning and 80.9% for deep learning. Overall, the results obtained using deep learning were superior to those obtained using conventional machine learning for both single and multiple IMUs. With regard to the convenience of use in self-fitness, the most feasible strategy was to utilize a single IMU on the right thigh.

A machine-learning method for classifying and analyzing foot placement: Application to manual material handling

Foot placement strategy is an essential aspect in the study of movement involving full body displacement. To get beyond a qualitative analysis, this paper provides a foot placement classification and analysis method that can be used in sports, rehabilitation or ergonomics. The method is based on machine learning using a weighted k-nearest neighbors algorithm. The learning phase is performed by an observer who classifies a set of trials. The algorithm then automatically reproduces this classification on subsequent sets. The method also provides detailed analysis of foot placement strategy, such as estimating the average foot placements for each class or visualizing the variability of strategies. An example of applying the method to a manual material handling task demonstrates its usefulness. During the lifting phase, the foot placements were classified into four groups: front, contralateral foot behind, ipsilateral foot behind, and parallel. The accuracy of the classification, assessed with a holdout method, is about 97%. In this example, the classification method makes it possible to observe and analyze the handler's foot placement strategies with regards to the performed task.

Machine learning approach to predict center of pressure trajectories in a complete gait cycle: a feedforward neural network vs. LSTM network

Center of pressure (COP) trajectories of human can maintain regulation of forward progression and stability of lateral sway during walking. The insole pressure system can only detect COP trajectories of each foot during single stance. In this study, we developed artificial neural network models that could present COP trajectories in an integrated coordinate system during a complete gait cycle using pressure information of the insole system. A feed forward artificial neural network (FFANN) and a long short-term memory (LSTM) model were developed. For FFANN, among 198 pressure sensors from Pedar-X insoles, proper input variables were selected using sequential forward selection to reduce input dimension. The LSTM model used all 198 signals as inputs because of its self-learning characteristic. As results of cross-validation, the FFANN model showed correlation coefficients of 0.98-0.99 and 0.93-0.95 in anterior/posterior and medial/lateral directions, respectively. For the LSTM model, correlation coefficients were similar to those of FFANN. However, the relative root mean square error (12.5%) of the FFANN model was higher than that (9.8%) of the LSTM model in medial/lateral direction (p = 0.03). This study can be used for quantitative evaluation of clinical diagnosis and rehabilitation status for patient with various diseases through further training using varied databases. Graphical abstract Architectures of neural networks developed in this study (a feed forward artificial neural network; b LSTM network).

Machine learning algorithms can classify outdoor terrain types during running using accelerometry data

BACKGROUND

Running is a popular physical activity that benefits health; however, running surface characteristics may influence loading impact and injury risk. Machine learning algorithms could automatically identify running surface from wearable motion sensors to quantify running exposures, and perhaps loading and injury risk for a runner.

RESEARCH QUESTION

(1) How accurately can machine learning algorithms identify surface type from three-dimensional accelerometer sensors? (2) Does the sensor count (single or two-sensor setup) affect model accuracy?

METHODS

Twenty-nine healthy adults (23.3 ± 3.6 years, 1.8 ± 0.1 m, and 63.6 ± 8.5 kg) participated in this study. Participants ran on three different surfaces (concrete, synthetic, woodchip) while fit with two three-dimensional accelerometers (lower-back and right tibia). Summary features (n = 208) were extracted from the accelerometer signals. Feature-based Gradient Boosting (GB) and signal-based deep learning Convolutional Neural Network (CNN) models were developed. Models were trained on 90% of the data and tested on the remaining 10%. The process was repeated five times, with data randomly shuffled between train-test splits, to quantify model performance variability.

RESULTS

All models and configurations achieved greater than 90% average accuracy. The highest performing models were the two-sensor GB and tibia-sensor CNN (average accuracy of 97.0 ± 0.7 and 96.1 ± 2.6%, respectively).

SIGNIFICANCE

Machine learning algorithms trained on running data from a single- or dual-sensor accelerometer setup can accurately distinguish between surfaces types. Automatic identification of surfaces encountered during running activities could help runners and coaches better monitor training load, improve performance, and reduce injury rates.

What Lies Beneath One’s Feet? Terrain Classification Using Inertial Data of Human Walk

The objective of this study was to investigate if the inertial data collected from normal human walk can be used to reveal the underlying terrain types. For this purpose, we recorded the gait patterns of normal human walk on six different terrain types with variation in hardness and friction using body mounted inertial sensors. We collected accelerations and angular velocities of 40 healthy subjects with two smartphones embedded inertial measurement units (MPU-6500) attached at two different body locations (chest and lower back). The recorded data were segmented with stride based segmentation approach and 194 tempo-spectral features were computed for each stride. We trained two machine learning classifiers, namely random forest and support vector machine, and cross validated the results with 10-fold cross-validation strategy. The classification tasks were performed on indoor–outdoor terrains, hard–soft terrains, and a combination of binary, ternary, quaternary, quinary and senary terrains. From the experimental results, the classification accuracies of 97% and 92% were achieved for indoor–outdoor and hard–soft terrains, respectively. The classification results for binary, ternary, quaternary, quinary and senary class classification were 96%, 94%, 92%, 90%, and 89%, respectively. These results demonstrate that the stride data collected with the low-level signals of a single IMU can be used to train classifiers and predict terrain types with high accuracy. Moreover, the problem at hand can be solved invariant of sensor type and sensor location.

Single Inertial Sensor-Based Neural Networks to Estimate COM-COP Inclination Angle During Walking

A biomechanical understanding of gait stability is needed to reduce falling risk. As a typical parameter, the COM-COP (center of mass-center of pressure) inclination angle (IA) could provide valuable insight into postural control and balance recovery ability. In this study, an artificial neural network (ANN) model was developed to estimate COM-COP IA based on signals using an inertial sensor. Also, we evaluated how different types of ANN and the cutoff frequency of the low-pass filter applied to input signals could affect the accuracy of the model. An inertial measurement unit (IMU) including an accelerometer, gyroscope, and magnetometer sensors was fabricated as a prototype. The COM-COP IA was calculated using a 3D motion analysis system including force plates. In order to predict the COM-COP IA, a feed-forward ANN and long-short term memory (LSTM) network was developed. As a result, the feed-forward ANN showed a relative root-mean-square error (rRMSE) of 15% while the LSTM showed an improved accuracy of 9% rRMSE. Additionally, the LSTM displayed a stable accuracy regardless of the cutoff frequency of the filter applied to the input signals. This study showed that estimating the COM-COP IA was possible with a cheap inertial sensor system. Furthermore, the neural network models in this study can be implemented in systems to monitor the balancing ability of the elderly or patients with impaired balancing ability.

Tracking Foot Drop Recovery Following Lumbar-Spine Surgery, Applying Multiclass Gait Classification Using Machine Learning Techniques

The ability to accurately perform human gait evaluation is critical for orthopedic foot and ankle surgeons in tracking the recovery process of their patients. The assessment of gait in an objective and accurate manner can lead to improvement in diagnoses, treatments, and recovery. Currently, visual inspection is the most common clinical method for evaluating the gait, but this method can be subjective and inaccurate. The aim of this study is to evaluate the foot drop condition in an accurate and clinically applicable manner. The gait data were collected from 56 patients suffering from foot drop with L5 origin gathered via a system based on inertial measurement unit sensors at different stages of surgical treatment. Various machine learning (ML) algorithms were applied to categorize the data into specific groups associated with the recovery stages. The results revealed that the random forest algorithm performed best out of the selected ML algorithms, with an overall 84.89% classification accuracy and 0.3785 mean absolute error for regression.

Reactive Power Optimization for Transient Voltage Stability in Energy Internet via Deep Reinforcement Learning Approach

The existence of high proportional distributed energy resources in energy Internet (EI) scenarios has a strong impact on the power supply-demand balance of the EI system. Decision-making optimization research that focuses on the transient voltage stability is of great significance for maintaining effective and safe operation of the EI. Within a typical EI scenario, this paper conducts a study of transient voltage stability analysis based on convolutional neural networks. Based on the judgment of transient voltage stability, a reactive power compensation decision optimization algorithm via deep reinforcement learning approach is proposed. In this sense, the following targets are achieved: the efficiency of decision-making is greatly improved, risks are identified in advance, and decisions are made in time. Simulations show the effectiveness of our proposed method.

An Extended Kalman Filter and Back Propagation Neural Network Algorithm Positioning Method Based on Anti-lock Brake Sensor and Global Navigation Satellite System Information

Telematics box (T-Box) chip-level Global Navigation Satellite System (GNSS) receiver modules usually suffer from GNSS information failure or noise in urban environments. In order to resolve this issue, this paper presents a real-time positioning method for Extended Kalman Filter (EKF) and Back Propagation Neural Network (BPNN) algorithms based on Antilock Brake System (ABS) sensor and GNSS information. Experiments were performed using an assembly in the vehicle with a T-Box. The T-Box firstly use automotive kinematical Pre-EKF to fuse the four wheel speed, yaw rate and steering wheel angle data from the ABS sensor to obtain a more accurate vehicle speed and heading angle velocity. In order to reduce the noise of the GNSS information, After-EKF fusion vehicle speed, heading angle velocity and GNSS data were used and low-noise positioning data were obtained. The heading angle speed error is extracted as target and part of low-noise positioning data were used as input for training a BPNN model. When the positioning is invalid, the well-trained BPNN corrected heading angle velocity output and vehicle speed add the synthesized relative displacement to the previous absolute position to realize a new position. With the data of high-precision real-time kinematic differential positioning equipment as the reference, the use of the dual EKF can reduce the noise range of GNSS information and concentrate good-positioning signals of the road within 5 m (i.e. the positioning status is valid). When the GNSS information was shielded (making the positioning status invalid), and the previous data was regarded as a training sample, it is found that the vehicle achieved 15 minutes position without GNSS information on the recycling line. The results indicated this new position method can reduce the vehicle positioning noise when GNSS information is valid and determine the position during long periods of invalid GNSS information.

Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry

Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data.